A simultaneous ~nonsymmetrical principal component analysis with a group structure (Q2711698)

An extension of principal components analysis on a reference subspace (PCAR) is proposed to the case where the same dependent variables have been measured on the same statistical units under two, or more, different observational conditions. Actually, a factorial method (R-SPCAR), jointly used with a rotation technique, has been proposed in order to analyse two (or more) sets of judgements on the same ~objects. Namely, R-SPCAR tries to explain the differences/similarities between the sets of judgements with respect to some characteristics of the objects. As the units belong to the same multidimensional space, orthogonal Procrustean rotation is profitably applied, jointly with PCAR, so as to enrich the interpretability of patterns on factorial planes.NEWLINENEWLINENEWLINEThe application context in which the method has been developed is that of sensory data analysis. The proposed technique is applied to a problem of agreement in the area of sensory data analysis for representing evaluation gaps between the perception of quality by wine experts and ordinary consumers. The proposed approach allows to explain the eventually detected gaps in terms of the physical-chemical characteristics of wines.